# Codestral vs GLM-4.7-Flash

> GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 30.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codestral-vs-glm-4-7-flash
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GLM-4.7-Flash leads 40.6 to 27.3.
- GLM-4.7-Flash is cheaper at $0.06 / $0.40 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Codestral accepts more context: 256K tokens versus 200K.
- GLM-4.7-Flash has downloadable open weights; the other is API-only.

## Snapshot

| | Codestral | GLM-4.7-Flash |
|---|---|---|
| Provider | Mistral AI | Z.ai (Zhipu) |
| Noometry Index | 30.6 | 38.8 |
| Rank | 290 | 180 |
| Context | 256K | 200K |
| Input $/M | $0.30 | $0.06 |
| Output $/M | $0.90 | $0.40 |
| Weights | Proprietary | Open |

## Coding

- Codestral: 27.3 (#321)
- GLM-4.7-Flash: 40.6 (#135)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1383 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |

## Reasoning

- Codestral: 19.8 (#251)
- GLM-4.7-Flash: 20.9 (#229)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1356 |

## Math

- Codestral: —
- GLM-4.7-Flash: 36.1 (#173)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 58.3% |
| LMArena Math | — | 1355 |

## Knowledge

- Codestral: —
- GLM-4.7-Flash: 35.5 (#184)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| GPQA Diamond | — | 60.5% |
| Vectara Hallucination Rate | — | 9.3% |
| LMArena Expert | — | 1357 |

## Multilingual

- Codestral: —
- GLM-4.7-Flash: 46.5 (#158)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| LMArena Non-English | — | 1330 |
| LMArena Chinese | — | 1403 |
| LMArena French | — | 1332 |
| LMArena German | — | 1337 |
| LMArena Korean | — | 1283 |
| LMArena Russian | — | 1332 |
| LMArena Spanish | — | 1350 |

## Instruction Following

- Codestral: —
- GLM-4.7-Flash: 70.1 (#167)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| LMArena Instruction Following | — | 1327 |

## Long Context

- Codestral: —
- GLM-4.7-Flash: 40.9 (#148)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| LMArena Longer Query | — | 1345 |

## Writing & Preference

- Codestral: —
- GLM-4.7-Flash: 47.4 (#210)

| Benchmark | Codestral | GLM-4.7-Flash |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1297 |
| EQ-Bench Creative Writing | — | 1125 |
| LMArena Multi-Turn | — | 1342 |

## FAQ

### Is Codestral better than GLM-4.7-Flash?

GLM-4.7-Flash is the stronger model overall, scoring 38.8 to 30.6 on the Noometry Index.

### Which is cheaper, Codestral or GLM-4.7-Flash?

GLM-4.7-Flash is cheaper. It lists at $0.06 per million input tokens and $0.40 per million output tokens; Codestral lists at $0.30 and $0.90.

### Is Codestral or GLM-4.7-Flash better for coding?

GLM-4.7-Flash scores higher on coding benchmarks: 40.6 versus 27.3 in the Noometry coding category.

### Which has the bigger context window?

Codestral does, with 256K tokens against 200K.

### How many benchmarks do Codestral and GLM-4.7-Flash share?

0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and GLM-4.7-Flash has 21.